An Ensemble-based Predictive Model for Examine Chronic Kidney Disease

Abstract

Abstract Chronic Kidney Disease (CKD) is a chronic ailment that involves a gradual decline in kidney function over time and lose their function over time. The focus of the research was to determine the most suitable classification algorithm for the diagnosis of CKD based on its classification report and performance factors. One approach to enhancing the accuracy of predictions is to combine multiple models such as Random Forest and Adaboost classifier were analyzed instead of relying on a single model. To put it another way, using an ensemble of models can lead to better predictive performance compared to using a single model alone. The results of the experiment showed that the stacking algorithms performed better than the other algorithms, producing an accuracy rate of 100.00%.